[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EN6TFFQVMXE5QB36JP93TA":3,"skill-same:01M7EN6TFFQVMXE5QB36JP93TA":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M7EN6TFFQVMXE5QB36JP93TA","landing-copy",null,"Use when writing the words on a single conversion page — the hero headline and subhead, the offer, the proof and testimonials, and one primary CTA — or diagnosing a page that gets traffic and does not convert, as a copy problem rather than a layout one. NOT the paid ad that drives the click (that is `ads`), NOT the visual layout the words sit in (that is `design`), NOT the experiment that picks the winning variant (that is `ab-testing`).","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Flanding-copy\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: landing-copy\ndescription: \"Use when writing the words on a single conversion page — the hero headline and subhead, the offer, the proof and testimonials, and one primary CTA — or diagnosing a page that gets traffic and does not convert, as a copy problem rather than a layout one. NOT the paid ad that drives the click (that is `ads`), NOT the visual layout the words sit in (that is `design`), NOT the experiment that picks the winning variant (that is `ab-testing`).\"\ntags: [landing-page, copywriting, conversion, hero-headline, cta, social-proof]\nrecommends: [ads, design, brand-voice, ab-testing, case-studies]\norigin: risco\n---\n\n# Landing Copy — The Words That Convert on One Page\n\n*Hook, offer, proof, CTA. You write the words a visitor reads top to bottom; you do not draw the layout, build the page, or write the ad that sent them.*\n\nThis skill owns **conversion copy for a single page**: a hero headline under ~8 words plus a benefit subhead, a top-to-bottom page skeleton, the offer stated as a benefit, proof slotted next to the ask, and one primary CTA repeated without competing. It is a copy job. The pixels are `design`'s, the React\u002FNext build is `nextjs`'s, the ad that drives the click is `ads`'s.\n\n## When to use\n\n- Writing or rewriting a hero: H1 + subhead + button copy.\n- Structuring a full landing\u002Fsales page (hook → problem → offer → proof → CTA → objections).\n- Choosing and writing one primary CTA and its repeated instances.\n- Turning features into benefits (\"AES-256 encryption\" → \"your security team signs off in days\").\n- Slotting proof — testimonials, metrics, logos, a guarantee — next to the ask.\n- Making the page headline *match* the ad\u002Femail that drove the click (message match).\n- Rescuing a page that gets traffic but does not convert — when the failure is the words.\n\n## When NOT to use (route to the sibling that owns it)\n\n- Visual layout, hierarchy, spacing, component system → `design` (`..\u002Fdesign\u002FSKILL.md`).\n- Building the page in code, form wiring, routing → `nextjs` (`..\u002Fnextjs\u002FSKILL.md`) \u002F `react`.\n- The paid Google\u002FMeta ad copy that drives traffic *to* the page → `ads`.\n- The brand's tone, voice rules, lexicon, do\u002Fdon't word list → `brand-voice`.\n- Ranking in organic search or getting cited by AI answer engines → `seo-geo`.\n- Designing and running the experiment that picks the winning variant → `ab-testing`.\n- Writing the standalone customer story as its own asset → `case-studies`.\n- A multi-channel launch plan, nurture emails, or campaign strategy → `marketing` (`..\u002Fmarketing\u002FSKILL.md`).\n\nBoundary in one line: **you own the words that convert on one page; `ads` owns the click that arrives, `design` owns the layout they sit in, `ab-testing` owns the proof of which words win.**\n\n## The conversion reality (calibrate, never promise)\n\nThese numbers set expectations. State them as a band; the moment you promise a flat conversion rate you are lying to the user.\n\n- **Cross-industry median is ~6.6%; strong pages in any vertical reach 10–15%+.** Per-vertical the spread is wide: Events & Entertainment ~12.3%, Financial Services ~8.4%, SaaS\u002FTech ~3.8%, Ecommerce ~2.35%, B2B services ~1–3%. *Why:* a SaaS team told \"you'll hit 12%\" was quoted the events median; quote the band for *their* vertical so the goal is real. (Foundry CRO benchmarks 2026, citing Unbounce's analysis of 464M visits \u002F 41k pages.)\n- **Visitors decide whether to stay in ~5 seconds, and ~80% rarely scroll past the fold.** *Why:* the hero is the single highest-leverage copy on the page — if it does not answer \"what is this and why should I care\" before a scroll, the rest is unread. (Hero-section research \u002F NN\u002Fg attention studies 2026.)\n\n## The four blocks — the spine of the page\n\nEvery conversion page is these four jobs, top to bottom. Each has a distinct question, a home on the page, and a failure mode. Diagnose a dead page by finding which block is weak.\n\n| Block | Must answer | Lives where | Failure mode if weak |\n| --- | --- | --- | --- |\n| **Hook** | \"What is this and why should I care?\" in \u003C5s | Hero, above the fold | Visitor bounces before scrolling; ~80% never see the rest |\n| **Offer** | \"What exactly do I get, and what does it cost me?\" | Right after the hook \u002F problem | Feature dump; reader can't tell what they walk away with |\n| **Proof** | \"Why should I believe you?\" | Adjacent to each CTA | Claims read as marketing; trust never forms |\n| **CTA** | \"What is the one thing to do next?\" | Hero, repeated down the page | Competing asks → decision fatigue → no click |\n\n## The hook\n\nThe H1 carries the *what*; the subhead carries the *benefit*; both must echo whatever the visitor clicked.\n\n- **H1 under ~8 words \u002F ~44 characters.** The constraint forces clarity, and a clear headline beats a clever one every time. If you can't say it in 8 words you don't understand the offer yet.\n- **Subhead carries the benefit** — who it's for and the outcome they get, in one clause.\n- **Message match:** the headline must echo the promise of the ad\u002Femail that drove the click. Aligning a single claim across ad + page has produced a 66% CVR lift in documented cases (and 212% from fixing message match alone). *You match the page to the ad; writing the ad is `ads`.*\n\n```text\nBad  — \"Reimagine The Future Of Financial Operations\"   (clever, 6 words, says nothing)\nGood — \"Expense reports done in 30 seconds\"             (clear, 5 words, names the outcome)\n         Subhead: For finance teams drowning in receipts — snap, submit, approved.\n```\n\n## The offer\n\nName the thing, the outcome, and the cost in effort or money. Lead with the outcome the buyer gets, then the mechanism that delivers it. This feature→benefit transform is the highest-impact copy shift on most pages.\n\nThe scaffold is **FAB** — Feature → Advantage → Benefit — but you stop at the benefit the reader cares about and back it with the mechanism as proof, not the other way round.\n\n```text\nBad  — \"Our platform has advanced AES-256 encryption.\"\nGood — \"Protect customer data with AES-256 encryption, so your security team\n         signs off in days, not months.\"\n```\n\nRule: every feature line answers \"so what?\" with an outcome. If it can't, cut it.\n\n## The proof\n\nBelief is built next to the ask, not in a wall of quotes elsewhere.\n\n- **3–5 specific, named testimonials, each with a concrete result.** \"Great product!\" persuades no one; \"cut our close time from 9 days to 2 — Maria, CFO at Lumen\" does. Specific beats superlative.\n- **Place proof adjacent to the primary CTA.** Social proof next to the ask has lifted conversion ~68% in documented cases; reviews\u002Ftestimonials are decisive for ~93% of buyers and ~88% trust them like a personal recommendation. *Why:* belief and the decision happen in the same moment — put the evidence where the click is.\n- Numbers, recognizable logos, and a risk-reversal (money-back, no card required) are proof too. One hard number outweighs three adjectives.\n- **Never fabricate proof.** If a metric, quote, or logo isn't real, mark `[[NEEDS PROOF]]` and ask the user — do not invent it.\n\n```text\nBad  — \"Loved by teams everywhere. World-class results!\"\nGood — \"We cut expense-report time 82% in the first month.\"\n         — Maria Ortiz, CFO, Lumen (47-person finance team)\n```\n\n## The CTA\n\nOne primary action, verb-led, repeated — not varied — down the page.\n\n- **One primary CTA per page.** Competing asks cause decision fatigue and lower conversion. The same action appears in the hero and again at each decision point; secondary links may exist but must not compete visually or verbally with the primary.\n- **Movement verbs, never \"Submit\".** \"Start free trial\", \"Get my quote\", \"See plans\" — the button states the value, not the form action.\n- **First-person framing often lifts clicks:** \"Start my free trial\" reads as the visitor's own intent. Pair the button with one line of friction-reducing microcopy (\"No credit card required\").\n\n```text\nBad  buttons — [Submit]            [Learn more]        [Contact sales]\nGood buttons — [Start my free trial]  ...repeated...  [Start my free trial]\n                under it: No credit card. Cancel anytime.\n```\n\n## Frameworks as scaffolds (fill with the reader's words)\n\nThese are skeletons to fill with the buyer's actual language, not fill-in templates:\n\n- **PAS** — Problem → Agitate → Solution. Best for pain-aware traffic.\n- **AIDA** — Attention → Interest → Desire → Action. Broad top-of-funnel.\n- **BAB** — Before → After → Bridge. Transformation stories.\n- **FAB** — Feature → Advantage → Benefit. The offer block.\n\nCommon stack: **PAS\u002FAIDA hook → FAB offer → proof → CTA.** How much you agitate the problem before the offer depends on traffic temperature (cold needs more, warm goes straight to the offer). Full explanations with fresh examples and the awareness-stage note → `references\u002Fframeworks.md`.\n\n## Anti-patterns → fix\n\n| Rationalization | Reality \u002F Fix |\n| --- | --- |\n| \"A clever headline will stand out\" | Clever is unclear. Name the outcome in \u003C8 words; clear beats clever. |\n| \"More features = more value shown\" | Feature dumps bury the benefit. Lead with the outcome, then the mechanism. |\n| \"Give them several CTAs to choose from\" | Choice kills conversion. One primary action, repeated, not varied. |\n| \"Any testimonials will do\" | Generic raves don't persuade. 3–5 named quotes with a hard result, near the CTA. |\n| \"World-class, cutting-edge, game-changing\" | Hype words signal AI-template copy. Replace with a number or a named result. |\n| \"The page can say its own thing\" | If the headline ignores the ad's promise, you lose the message-match lift. Echo the click. |\n| \"Promise them a 12% conversion rate\" | Never promise a flat number. Quote the band for their vertical. |\n| \"I'll invent a plausible metric\" | Never. Mark `[[NEEDS PROOF]]` and ask the user. |\n\n## Page skeleton + worked example\n\nThe annotated top-to-bottom skeleton (hook → problem → offer → proof → CTA → objections\u002FFAQ → final CTA), with one fully worked B2B SaaS example and the variable slots marked, lives in `references\u002Fpage-skeleton.md`. Start there when you write a full page rather than a single block.\n\n## Verify your copy\n\nRun `scripts\u002Fverify.sh` over the file you wrote (or your project) before claiming done. It is a read-only, dependency-free static check: H1 length, exactly one primary CTA verb (flags competing asks), presence of a proof block and a benefit subhead, a banlist of hype\u002FAI-tell phrases, and a \"Submit\" warning. It warns on soft issues and exits non-zero only on hard ones (no CTA, no proof). It is a backstop, not the judgement — the four-block table is.\n\n## See also\n\n- `..\u002Fdesign\u002FSKILL.md` — the pixels: layout, hierarchy, the visual system the words sit in.\n- `..\u002Fnextjs\u002FSKILL.md` — the build: rendering the page in code.\n- `..\u002Fmarketing\u002FSKILL.md` — the broader campaign: email sequences, channels, launch arc.\n- `ads` — the paid ad copy that drives the click (route here; you only match the page to it).\n- `ab-testing` — the experiment that proves which headline\u002FCTA wins.\n- `case-studies` · `brand-voice` · `seo-geo` — the proof asset, the voice rules, the search layer.\n- References: `references\u002Fframeworks.md`, `references\u002Fpage-skeleton.md`.\n","# Landing Copy — The Words That Convert on One Page\n\n*Hook, offer, proof, CTA. You write the words a visitor reads top to bottom; you do not draw the layout, build the page, or write the ad that sent them.*\n\nThis skill owns **conversion copy for a single page**: a hero headline under ~8 words plus a benefit subhead, a top-to-bottom page skeleton, the offer stated as a benefit, proof slotted next to the ask, and one primary CTA repeated without competing. It is a copy job. The pixels are `design`'s, the React\u002FNext build is `nextjs`'s, the ad that drives the click is `ads`'s.\n\n## When to use\n\n- Writing or rewriting a hero: H1 + subhead + button copy.\n- Structuring a full landing\u002Fsales page (hook → problem → offer → proof → CTA → objections).\n- Choosing and writing one primary CTA and its repeated instances.\n- Turning features into benefits (\"AES-256 encryption\" → \"your security team signs off in days\").\n- Slotting proof — testimonials, metrics, logos, a guarantee — next to the ask.\n- Making the page headline *match* the ad\u002Femail that drove the click (message match).\n- Rescuing a page that gets traffic but does not convert — when the failure is the words.\n\n## When NOT to use (route to the sibling that owns it)\n\n- Visual layout, hierarchy, spacing, component system → `design` (`..\u002Fdesign\u002FSKILL.md`).\n- Building the page in code, form wiring, routing → `nextjs` (`..\u002Fnextjs\u002FSKILL.md`) \u002F `react`.\n- The paid Google\u002FMeta ad copy that drives traffic *to* the page → `ads`.\n- The brand's tone, voice rules, lexicon, do\u002Fdon't word list → `brand-voice`.\n- Ranking in organic search or getting cited by AI answer engines → `seo-geo`.\n- Designing and running the experiment that picks the winning variant → `ab-testing`.\n- Writing the standalone customer story as its own asset → `case-studies`.\n- A multi-channel launch plan, nurture emails, or campaign strategy → `marketing` (`..\u002Fmarketing\u002FSKILL.md`).\n\nBoundary in one line: **you own the words that convert on one page; `ads` owns the click that arrives, `design` owns the layout they sit in, `ab-testing` owns the proof of which words win.**\n\n## The conversion reality (calibrate, never promise)\n\nThese numbers set expectations. State them as a band; the moment you promise a flat conversion rate you are lying to the user.\n\n- **Cross-industry median is ~6.6%; strong pages in any vertical reach 10–15%+.** Per-vertical the spread is wide: Events & Entertainment ~12.3%, Financial Services ~8.4%, SaaS\u002FTech ~3.8%, Ecommerce ~2.35%, B2B services ~1–3%. *Why:* a SaaS team told \"you'll hit 12%\" was quoted the events median; quote the band for *their* vertical so the goal is real. (Foundry CRO benchmarks 2026, citing Unbounce's analysis of 464M visits \u002F 41k pages.)\n- **Visitors decide whether to stay in ~5 seconds, and ~80% rarely scroll past the fold.** *Why:* the hero is the single highest-leverage copy on the page — if it does not answer \"what is this and why should I care\" before a scroll, the rest is unread. (Hero-section research \u002F NN\u002Fg attention studies 2026.)\n\n## The four blocks — the spine of the page\n\nEvery conversion page is these four jobs, top to bottom. Each has a distinct question, a home on the page, and a failure mode. Diagnose a dead page by finding which block is weak.\n\n| Block | Must answer | Lives where | Failure mode if weak |\n| --- | --- | --- | --- |\n| **Hook** | \"What is this and why should I care?\" in \u003C5s | Hero, above the fold | Visitor bounces before scrolling; ~80% never see the rest |\n| **Offer** | \"What exactly do I get, and what does it cost me?\" | Right after the hook \u002F problem | Feature dump; reader can't tell what they walk away with |\n| **Proof** | \"Why should I believe you?\" | Adjacent to each CTA | Claims read as marketing; trust never forms |\n| **CTA** | \"What is the one thing to do next?\" | Hero, repeated down the page | Competing asks → decision fatigue → no click |\n\n## The hook\n\nThe H1 carries the *what*; the subhead carries the *benefit*; both must echo whatever the visitor clicked.\n\n- **H1 under ~8 words \u002F ~44 characters.** The constraint forces clarity, and a clear headline beats a clever one every time. If you can't say it in 8 words you don't understand the offer yet.\n- **Subhead carries the benefit** — who it's for and the outcome they get, in one clause.\n- **Message match:** the headline must echo the promise of the ad\u002Femail that drove the click. Aligning a single claim across ad + page has produced a 66% CVR lift in documented cases (and 212% from fixing message match alone). *You match the page to the ad; writing the ad is `ads`.*\n\n```text\nBad  — \"Reimagine The Future Of Financial Operations\"   (clever, 6 words, says nothing)\nGood — \"Expense reports done in 30 seconds\"             (clear, 5 words, names the outcome)\n         Subhead: For finance teams drowning in receipts — snap, submit, approved.\n```\n\n## The offer\n\nName the thing, the outcome, and the cost in effort or money. Lead with the outcome the buyer gets, then the mechanism that delivers it. This feature→benefit transform is the highest-impact copy shift on most pages.\n\nThe scaffold is **FAB** — Feature → Advantage → Benefit — but you stop at the benefit the reader cares about and back it with the mechanism as proof, not the other way round.\n\n```text\nBad  — \"Our platform has advanced AES-256 encryption.\"\nGood — \"Protect customer data with AES-256 encryption, so your security team\n         signs off in days, not months.\"\n```\n\nRule: every feature line answers \"so what?\" with an outcome. If it can't, cut it.\n\n## The proof\n\nBelief is built next to the ask, not in a wall of quotes elsewhere.\n\n- **3–5 specific, named testimonials, each with a concrete result.** \"Great product!\" persuades no one; \"cut our close time from 9 days to 2 — Maria, CFO at Lumen\" does. Specific beats superlative.\n- **Place proof adjacent to the primary CTA.** Social proof next to the ask has lifted conversion ~68% in documented cases; reviews\u002Ftestimonials are decisive for ~93% of buyers and ~88% trust them like a personal recommendation. *Why:* belief and the decision happen in the same moment — put the evidence where the click is.\n- Numbers, recognizable logos, and a risk-reversal (money-back, no card required) are proof too. One hard number outweighs three adjectives.\n- **Never fabricate proof.** If a metric, quote, or logo isn't real, mark `[[NEEDS PROOF]]` and ask the user — do not invent it.\n\n```text\nBad  — \"Loved by teams everywhere. World-class results!\"\nGood — \"We cut expense-report time 82% in the first month.\"\n         — Maria Ortiz, CFO, Lumen (47-person finance team)\n```\n\n## The CTA\n\nOne primary action, verb-led, repeated — not varied — down the page.\n\n- **One primary CTA per page.** Competing asks cause decision fatigue and lower conversion. The same action appears in the hero and again at each decision point; secondary links may exist but must not compete visually or verbally with the primary.\n- **Movement verbs, never \"Submit\".** \"Start free trial\", \"Get my quote\", \"See plans\" — the button states the value, not the form action.\n- **First-person framing often lifts clicks:** \"Start my free trial\" reads as the visitor's own intent. Pair the button with one line of friction-reducing microcopy (\"No credit card required\").\n\n```text\nBad  buttons — [Submit]            [Learn more]        [Contact sales]\nGood buttons — [Start my free trial]  ...repeated...  [Start my free trial]\n                under it: No credit card. Cancel anytime.\n```\n\n## Frameworks as scaffolds (fill with the reader's words)\n\nThese are skeletons to fill with the buyer's actual language, not fill-in templates:\n\n- **PAS** — Problem → Agitate → Solution. Best for pain-aware traffic.\n- **AIDA** — Attention → Interest → Desire → Action. Broad top-of-funnel.\n- **BAB** — Before → After → Bridge. Transformation stories.\n- **FAB** — Feature → Advantage → Benefit. The offer block.\n\nCommon stack: **PAS\u002FAIDA hook → FAB offer → proof → CTA.** How much you agitate the problem before the offer depends on traffic temperature (cold needs more, warm goes straight to the offer). Full explanations with fresh examples and the awareness-stage note → `references\u002Fframeworks.md`.\n\n## Anti-patterns → fix\n\n| Rationalization | Reality \u002F Fix |\n| --- | --- |\n| \"A clever headline will stand out\" | Clever is unclear. Name the outcome in \u003C8 words; clear beats clever. |\n| \"More features = more value shown\" | Feature dumps bury the benefit. Lead with the outcome, then the mechanism. |\n| \"Give them several CTAs to choose from\" | Choice kills conversion. One primary action, repeated, not varied. |\n| \"Any testimonials will do\" | Generic raves don't persuade. 3–5 named quotes with a hard result, near the CTA. |\n| \"World-class, cutting-edge, game-changing\" | Hype words signal AI-template copy. Replace with a number or a named result. |\n| \"The page can say its own thing\" | If the headline ignores the ad's promise, you lose the message-match lift. Echo the click. |\n| \"Promise them a 12% conversion rate\" | Never promise a flat number. Quote the band for their vertical. |\n| \"I'll invent a plausible metric\" | Never. Mark `[[NEEDS PROOF]]` and ask the user. |\n\n## Page skeleton + worked example\n\nThe annotated top-to-bottom skeleton (hook → problem → offer → proof → CTA → objections\u002FFAQ → final CTA), with one fully worked B2B SaaS example and the variable slots marked, lives in `references\u002Fpage-skeleton.md`. Start there when you write a full page rather than a single block.\n\n## Verify your copy\n\nRun `scripts\u002Fverify.sh` over the file you wrote (or your project) before claiming done. It is a read-only, dependency-free static check: H1 length, exactly one primary CTA verb (flags competing asks), presence of a proof block and a benefit subhead, a banlist of hype\u002FAI-tell phrases, and a \"Submit\" warning. It warns on soft issues and exits non-zero only on hard ones (no CTA, no proof). It is a backstop, not the judgement — the four-block table is.\n\n## See also\n\n- `..\u002Fdesign\u002FSKILL.md` — the pixels: layout, hierarchy, the visual system the words sit in.\n- `..\u002Fnextjs\u002FSKILL.md` — the build: rendering the page in code.\n- `..\u002Fmarketing\u002FSKILL.md` — the broader campaign: email sequences, channels, launch arc.\n- `ads` — the paid ad copy that drives the click (route here; you only match the page to it).\n- `ab-testing` — the experiment that proves which headline\u002FCTA wins.\n- `case-studies` · `brand-voice` · `seo-geo` — the proof asset, the voice rules, the search layer.\n- References: `references\u002Fframeworks.md`, `references\u002Fpage-skeleton.md`.\n",{"name":5,"tags":24,"origin":31,"recommends":32,"description":7},[25,26,27,28,29,30],"landing-page","copywriting","conversion","hero-headline","cta","social-proof","risco",[33,34,35,36,37],"ads","design","brand-voice","ab-testing","case-studies","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Flanding-copy",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill landing-copy",{"tool":52,"command":53},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill landing-copy",{"tool":55,"command":56},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill landing-copy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Flanding-copy\u002FSKILL.md",true,[60,66,70,74],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"evals\u002Fcases.yaml","REFERENCE","参考文档",4532,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Flanding-copy\u002Fevals\u002Fcases.yaml",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"evals\u002FREADME.md",1182,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Flanding-copy\u002Fevals\u002FREADME.md",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fframeworks.md",3284,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Flanding-copy\u002Freferences\u002Fframeworks.md",{"path":75,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fpage-skeleton.md",4029,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Flanding-copy\u002Freferences\u002Fpage-skeleton.md",[79,87,92,99,106,113],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":86},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":88,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":86},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":86},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":86},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":86},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":86},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]